global: accepts file_path and/or pre loaded YAML object

* API - validation method now to be used with file_path= parameter,
  and optionally a data object that represents the loaded YAML structure.
  This avoids loaded the YAML file twice which can be an overhead for
  larger YAML files.

* README - updated readme.

* Release - version 0.1.10

Signed-off-by: Eamonn Maguire <eamonnmag@gmail.com>

README.md

@@ -33,7 +33,7 @@ submission_file_validator = SubmissionFileValidator()
 submission_file_path = 'submission.yaml'
 
 # the validate method takes a string representing the file path. 
-is_valid_submission_file = submission_file_validator.validate(submission_file_path)
+is_valid_submission_file = submission_file_validator.validate(file_path=submission_file_path)
 
 # if there are any error messages, they are retrievable through this call
 submission_file_validator.get_messages()
@@ -47,8 +47,25 @@ from hepdata_validator.data_file_validator import DataFileValidator
 data_file_validator = DataFileValidator()
 
 # the validate method takes a string representing the file path.
-data_file_validator.validate('data.yaml')
+data_file_validator.validate(file_path='data.yaml')
 
 # if there are any error messages, they are retrievable through this call
 data_file_validator.get_messages()
 ```
+
+Optionally, if you have already loaded the YAML object, then you can pass it through
+as a data object. You must also pass through the file_path since this is used as a key
+for the error message lookup map.
+
+```python
+
+from hepdata_validator.data_file_validator import DataFileValidator
+import yaml
+
+file = yaml.load(open('data.yaml', 'r'))
+data_file_validator = DataFileValidator()
+
+data_file_validator.validate(file_path='data.yaml', data=file_contents)
+
+data_file_validator.get_messages('data.yaml')
+```

hepdata_validator/__init__.py

@@ -18,20 +18,26 @@ class Validator(object):
     def __init__(self):
         self.messages = {}
 
-    def validate(self, file_path):
+    def validate(self, **kwargs):
         """
         Validates a file.
         :param file_path: path to file to be loaded.
+        :param data: pre loaded YAML object (optional).
         :return: true if valid, false otherwise
         """
         schema = json.load(open(self.schema_file, 'r'))
 
-        try:
+        data = kwargs.pop("data", None)
+        file_path = kwargs.pop("file_path", None)
+
+        if data is None:
+
             try:
                 data = yaml.load(open(file_path, 'r'), Loader=yaml.CLoader)
             except: #pragma: no cover
                 data = yaml.load(open(file_path, 'r')) #pragma: no cover
 
+        try:
             validate(data, schema)
 
         except ValidationError as ve:

hepdata_validator/submission_file_validator.py

@@ -16,7 +16,13 @@ class SubmissionFileValidator(Validator):
     schema_file = base_path + '/schemas/submission_schema.json'
     additonal_info_schema = base_path + '/schemas/additional_info_schema.json'
 
-    def validate(self, file_path):
+    def validate(self, **kwargs):
+        """
+        Validates a submission file
+        :param file_path: path to file to be loaded.
+        :param data: pre loaded YAML object (optional).
+        :return: Bool to indicate the validity of the file.
+        """
         try:
             submission_file_schema = json.load(
                     open(self.schema_file, 'r'))
@@ -26,11 +32,18 @@ def validate(self, file_path):
 
             # even though we are using the yaml package to load,
             # it supports JSON and YAML
-            try:
-                # We try to load using the CLoader for speed improvements.
-                data = yaml.load_all(open(file_path, 'r'), Loader=yaml.CLoader)
-            except: #pragma: no cover
-                data = yaml.load_all(open(file_path, 'r')) #pragma: no cover
+            data = kwargs.pop("data", None)
+            file_path = kwargs.pop("file_path", None)
+
+            if file_path is None:
+                raise LookupError("file_path argument must be supplied")
+
+            if data is None:
+                try:
+                    # We try to load using the CLoader for speed improvements.
+                    data = yaml.load_all(open(file_path, 'r'), Loader=yaml.CLoader)
+                except Exception as e: #pragma: no cover
+                    data = yaml.load_all(open(file_path, 'r')) #pragma: no cover
 
             for data_item in data:
                 if data_item is None:

setup.py

@@ -49,8 +49,8 @@ def run_tests(self):
 
 setup(
     name='hepdata_validator',
-    version='0.1.9',
-    summary='0.1.9 release',
+    version='0.1.10',
+    summary='0.1.10 release',
     url='https://github.com/hepdata/hepdata-validator',
     license='GPLv2',
     author='Eamonn Maguire',

testsuite/validation_test.py

@@ -1,5 +1,8 @@
 import os
 import unittest
+
+import yaml
+
 from hepdata_validator.data_file_validator import DataFileValidator
 from hepdata_validator.submission_file_validator import SubmissionFileValidator
 
@@ -24,7 +27,8 @@ def test_valid_submission_yaml(self):
         self.validator = SubmissionFileValidator()
         valid_sub_yaml = os.path.join(self.base_dir, self.valid_file)
 
-        self.validator.validate(valid_sub_yaml)
+        sub_yaml_obj = yaml.load_all(open(valid_sub_yaml, 'r'))
+        self.validator.validate(file_path=valid_sub_yaml, data=sub_yaml_obj)
         self.validator.print_errors(valid_sub_yaml)
 
         print 'Valid\n'
@@ -37,7 +41,7 @@ def test_valid_submission_yaml_with_empty_section(self):
         self.validator = SubmissionFileValidator()
         valid_sub_yaml = os.path.join(self.base_dir, self.valid_empty_file)
 
-        self.assertEqual(self.validator.validate(valid_sub_yaml), True)
+        self.assertEqual(self.validator.validate(file_path=valid_sub_yaml), True)
         self.validator.print_errors(valid_sub_yaml)
 
 
@@ -50,7 +54,7 @@ def test_valid_submission_yaml_with_license(self):
         valid_sub_yaml = os.path.join(self.base_dir,
                                       self.valid_license_file)
 
-        self.assertEqual(self.validator.validate(valid_sub_yaml), True)
+        self.assertEqual(self.validator.validate(file_path=valid_sub_yaml), True)
 
         self.validator.print_errors(valid_sub_yaml)
 
@@ -62,7 +66,7 @@ def test_invalid_submission_yaml(self):
         invalid_sub_yaml = os.path.join(self.base_dir, self.invalid_file)
 
         self.assertEqual(self.validator.validate(
-            invalid_sub_yaml), False
+            file_path=invalid_sub_yaml), False
         )
 
         self.validator.print_errors(invalid_sub_yaml)
@@ -101,13 +105,13 @@ def setUp(self):
 
     def test_valid_yaml_file(self):
         print '___DATA_VALIDATION: Testing valid yaml submission___'
-        is_valid = self.validator.validate(self.valid_file_yaml)
+        is_valid = self.validator.validate(file_path=self.valid_file_yaml)
         self.validator.print_errors(self.valid_file_yaml)
         self.assertEqual(is_valid, True)
 
     def test_invalid_yaml_file(self):
         print '___DATA_VALIDATION: Testing invalid yaml submission___'
-        self.assertEqual(self.validator.validate(self.invalid_file_yaml),
+        self.assertEqual(self.validator.validate(file_path=self.invalid_file_yaml),
                          False)
 
         self.validator.print_errors(self.invalid_file_yaml)
@@ -116,14 +120,14 @@ def test_invalid_yaml_file(self):
 
     def test_valid_file_with_percent_errors(self):
         print '___DATA_VALIDATION: Testing valid yaml percent error ___'
-        self.assertEqual(self.validator.validate(self.valid_file_error_percent_yaml),
+        self.assertEqual(self.validator.validate(file_path=self.valid_file_error_percent_yaml),
                          False)
         self.validator.print_errors(self.valid_file_error_percent_yaml)
         print 'Invalid\n'
 
     def test_valid_json_file(self):
         print '___DATA_VALIDATION: Testing valid json submission___'
-        is_valid = self.validator.validate(self.valid_file_json)
+        is_valid = self.validator.validate(file_path=self.valid_file_json)
         self.validator.print_errors(self.valid_file_json)
         self.assertEqual(is_valid, True)
 
@@ -132,7 +136,7 @@ def test_valid_json_file(self):
 
     def test_invalid_json_file(self):
         print '___DATA_VALIDATION: Testing invalid json submission___'
-        self.assertEqual(self.validator.validate(self.invalid_file_json),
+        self.assertEqual(self.validator.validate(file_path=self.invalid_file_json),
                          False)
         self.validator.print_errors(self.invalid_file_json)
         print 'Invalid\n'